Improving non-negative positive-unlabeled learning for news headline classification

HIGHLIGHTS

  • who: ZHANLIN JI and colleagues from the College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China have published the research: Improving non-negative Positive-Unlabeled learning for news headline classification, in the Journal: (JOURNAL)
  • what: The concept of PU learning is proposed for the first time, and a two-step methods procedure is provided, which established a theoretical basis for the subsequent research. In the current paper, to the best of the knowledge , VAT is introduced for use in nnPU learning for the first time. In the experiments conducted on the . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?